Академический Документы
Профессиональный Документы
Культура Документы
Increasing trend of wearables and multimodal interface for human activity MARK
monitoring: A review
Preeti Kumari , Lini Mathew, Poonam Syal
Department of Electrical Engineering, National Institute of Technical Teacher's Training and Research, Sector-26, Chandigarh 160019, India
A R T I C L E I N F O A BS T RAC T
Keywords: Activity recognition technology is one of the most important technologies for life-logging and for the care of
Human activity monitoring elderly persons. Elderly people prefer to live in their own houses, within their own locality. If, they are capable to
Human Computer Interface do so, several benets can follow in terms of society and economy. However, living alone may have high risks.
Wearable sensors Wearable sensors have been developed to overcome these risks and these sensors are supposed to be ready for
Smart sensors
medical uses. It can help in monitoring the wellness of elderly persons living alone by unobtrusively monitoring
Multimodal interface
Biomedical
their daily activities. The study aims to review the increasing trends of wearable devices and need of multimodal
Shared control architecture recognition for continuous or discontinuous monitoring of human activity, biological signals such as
Electroencephalogram (EEG), Electrooculogram (EOG), Electromyogram (EMG), Electrocardiogram (ECG)
and parameters along with other symptoms. This can provide necessary assistance in times of ominous need,
which is crucial for the advancement of disease-diagnosis and treatment. Shared control architecture with
multimodal interface can be used for application in more complex environment where more number of
commands is to be used to control with better results in terms of controlling.
1. Introduction machines (SVM) (Gunn, 1998). Data acquisition process has two
dierent approaches: one is the traditional approach which uses
Activity monitoring aims to monitor the actions of agents obtained external sensors such as cameras or other monitoring devices (Lin,
from a number of observations on the actions of agents and conditions 2009) and the second one is the newly introduced approach which uses
of the environment. Activity recognition plays an important role in wearable wireless sensors. Both the approaches use dierent types of
ambient living environments to assess changes from the normal electrodes to acquire the physiological signals. These electrodes can be
behavior of elderly people (Uslu et al., 2013). The objective of activity active or passive electrodes as per requirement and the positions of the
monitoring is to analyze or interpret the ongoing events from data electrode placement can be signal-dependent as well as application-
automatically. Since 1980s, this eld has grasped the attention of many dependent. For example, to acquire the EOG signal for vertical move-
researchers due to its ability to provide personalized support for several ment of eyeballs, electrodes are placed above and below the eyes and
applications which include patient monitoring, surveillance and many for horizontal movement of eyeballs, electrodes are placed on right side
dierent varieties of systems involving interactions between machines of right eye and left side of left eye. For EEG recording, electrodes are
and persons such as Brain-Computer Interfaces (BCI). placed according to the 1020 International system. In the traditional
Activity monitoring includes two processes: data acquisition fol- approach, sensors are xed at predetermined places, so the conjectures
lowed by classication of acquired data. The acquisition of data are fully based on the discretionary interaction between person under
includes acquiring the bio-signals and signal preprocessing. The bio- monitoring and sensors used. Examples of external sensing approach
signals can be EEG, EOG, EMG or ECG depending upon the applica- are Intelligent Homes (Englebienne and Krose, 2010; Tolstikov et al.,
tion. Signal preprocessing includes amplifying, ltering, averaging, 2011; Yang et al., 2011; Sarkar et al., 2011). However, in the second
extracting relevant features to be used as training data for classier etc. approach, sensors are attached to the human body. Human Activity
For classication, various methods are used such as least squares Recognition (HAR) systems based on wearable sensors can be categor-
(Marquardt, 1963), Knearest neighbors (k-NN) (Cunningham and ized in two stages. One is learning approach, may be supervised,
Delany, 2007), hidden Markov method, articial neural networks unsupervised or semi-supervised. In the second stage, depending on
(ANN) (Hopeld, 1988) decision tree classication and support vector the response time, these approaches may be either oine or online.
Corresponding author.
E-mail addresses: pgrr.2403@gmail.com (P. Kumari), lenimathew@yahoo.com (L. Mathew).
http://dx.doi.org/10.1016/j.bios.2016.12.001
Received 15 September 2016; Received in revised form 1 December 2016; Accepted 1 December 2016
Available online 02 December 2016
0956-5663/ 2016 Elsevier B.V. All rights reserved.
P. Kumari et al. Biosensors and Bioelectronics 90 (2017) 298307
Sensor data is collected and after analysis of acquired data, made these
data available to the patients, caretakers, wearers or healthcare
professionals. The goal is to improve the management and care-
delivery, to engage patients and encourage independent living
(Rodgers et al., 2015).
2. Wearable Sensors
Fig. 2. Representation of Human Activity Recognition (HAR) system in block diagram (Malhi, 2010).
299
P. Kumari et al. Biosensors and Bioelectronics 90 (2017) 298307
Fig. 3. (a). Ring Sensor & its Schematic Diagram. (b). Smart Shirt and its Sensory Architecture.
tions, reman cloths, diving cloths or cloths for any specic function we design parameters have been derived (Bagade et al., 2014). Some basic
want. requirements are discussed below:
Other applications in health care are biofeedback respiratory
system (Liu et al., 2011), mental stress assessment (Seoane et al., 2.1.1. Aesthetics
2014), rehabilitation system (Patel et al., 2012), weight lifting exercise Appearance is so important that many top companies are working
(Velloso et al., 2013), vision sensor in real-time (Peixoto et al., 2001), in partnership with the fashion industry to make these wearable
posture & movement wearable sensor (Ugulino et al., 2012). Apart devices fashionable and more attractive.
from health-care systems, wearables are widely used in various other
elds such as to provide training support for athletes, to monitor the 2.1.2. Size
persons who work at hazardous places. It also facilitates physically- Wearable devices must be compact enough so that they can easily t
disabled people to continue enjoying their independence for longer onto the human body. It should be comfortable to the wearer as well as
time span. It can give mental peace to the elderly persons through a they must have more features integrated into the same space.
simple panic button (Versel, 2012; Alert Devices for the Elderly, 2016;
Mobile phones to come with panic button from, 2017, 2016) and 2.1.3. Water tolerance
provides assurance to family members and friends. As the wearable device has to go everywhere along with human
body, it should be tolerant of the environmental conditions such as
2.1. Basic requirements of a wearable device temperature, water droplets, moisture, and sweat for continuous
monitoring of the human behavior.
Before developing a wearable system, it is essential to have a clear
idea about the basic requirements and designing challenges for any 2.1.4. Power consumption
wearable device. There are always hardware and software constraints Wearable devices are powered by a battery. For monitoring of
beginning from low-energy operations, light-weight and safety require- human behavior continuously 247, power requirement will be very
ments. While person is placing the wearable sensor on his/her body, high. Among all the system-components, communication system con-
the chances of thermal injury must be considered and should be sumes most of the energy. An autonomous wireless wearable sensor
reduced by controlling the sensing and wireless frequency and radio node having exible energy harvesting mechanism has been presented
duty cycle of wearable sensor. A novel optimization framework has which is equipped with ultralow power management circuit. This
been proposed for considering safety requirements as well as sustain- exible power management circuit can transfer maximum electrical
ability requirements based on the human physiology and system level power from solar energy to give power to the wireless sensor node (Toh
300
P. Kumari et al. Biosensors and Bioelectronics 90 (2017) 298307
et al., 2014). Reduction of power consumption of these devices poses 3. Architecture of wearable system
requirement of special features in Micro Controller Unit and rmware
algorithms. ARM architecture is very popular for wearable systems Architecture of wearable system can be explained with the help of a
because of its best performance. Also, ANT+, Bluetooth Low Energy block diagram representation as shown in Fig. 4. It consists of dierent
(BLE) are energy ecient wireless technologies. blocks namely: Power supply, display, wireless connectivity, motion
sensing and application processor. Micro-Electro-Mechanical Systems
(MEMS) sensors monitor the movement of a human body in every
2.1.5. Wireless communication
dimension. The examples of motion sensor or MEMS sensor may
For continuous monitoring of human behavior, wireless connectiv-
include accelerometers, magnetometers, and gyroscopes. Analogue
ity is essential, as the person or the wearer cannot move freely so far
sensors are biometric sensors such as heart rate monitors and EEG,
with wires. Also, the person will not feel comfortable being surrounded
EMG. Analogue Front End (AFE) basically preprocessed the data
by wires. Apart from this, they may need to interact with more than one
acquired from sensors. It contains operational ampliers, lters, and
device. According to the type and features oered, the device may
A/D Convertors. User Interface (UI) systems are used for interaction
support dierent wireless protocols such as Wi-Fi, ANT+, and IEEE
between human being and wearable device which is an important
802.15.4 based protocol. Dierent data source may generate heavy
consideration.
time-varying trac which may lead to intolerant abeyancy in wireless
Capacitive touch sensing is the most preferred User Interface
wearable sensors. Moreover, delivery of data in real-time, packet loss
available today. UI elements are indicators used for alerts implementa-
and fading in data transmission induced by movement as well as
tion from the device to the user as well as from user to the device. Pulse
surrounding environment is a big challenge.
width modulation (PWM) is used to drive these UI elements. Among all
these components of wearable system, one of the most important
2.1.6. Operating system components is application processor and is selected very carefully. The
Sometimes, the wearable device may need a specic operating selection of application processor depends on the type, features and
system such as Android depending on the features being oered. For characteristics of the device. The latest microcontrollers are compatible
example, a smart watch designed to be an extension of a mobile phone with most of the wearable systems. MCUs are compact and can
needs to run a specic advanced operating system. integrate a number of functions on a single chip which is very
Day by day, new trends can be seen in the eld of Wearable system important to reduce the overall size and cost of a wearable device.
which has enhanced features. For example, shirt or other cloths with For example, 32 bit ARM architecture is a very popular Central
all-fabric keyboard made by conductive thread can be washed in the processing Unit (CPU) technology for wearable systems as it shows
machine same as ordinary cloths. So, it is water durable which is one of best performance in terms of computation and energy eciency
the basic requirements for a wearable device. Computerized cloths can (Ramasamy et al., 2014). For Some advanced applications, wearable
be the next generation for computers and other devices which does not systems may need a separate co-processor to ooad the sensor data
require strap of electronics into our body. Although a huge amount of from the main processor. This is needed when the system has to load
eort is being made in the wearable sensors, challenges like user- the sensor data and at the same time, it has to analyze it together in real
acceptance, low power consumption, interference in wireless systems time, requiring full CPU attention. This function is known as sensor
are still to be resolved for better usability and functionality of these hub or sensor fusion.
wearable devices.
Fig. 4. Block diagram representation of a wireless wearable system (Ramasamy et al., 2014).
301
P. Kumari et al. Biosensors and Bioelectronics 90 (2017) 298307
302
P. Kumari et al. Biosensors and Bioelectronics 90 (2017) 298307
emotions considered in this work were happy, sad, angry, relaxed. The
concept of smart skins has been proposed in some recent works (Cook
et al., 2013). Smart skins are intelligent cognitive skins that sense,
Fig. 9. Evolution of EEG from conventional system to In-Ear-EEG.
wirelessly communicate, and will be capable of modifying environ-
mental or physiological parameters using very simple passive RFID
technology sticker in the future. Smart skins are zero-power devices
meaning they rummage their own energy using ambient energy such as have dierent angles and side views. Therefore, there is a need for
electromagnetic, solar, mechanical, thermal, or RFID/Radar-based further research for improving the recognition rate of facial expressions
inquisition techniques. The concept can also be extended as body- with various angles and litter of face (Siddiqi et al., 2015). Human body
wearable skins for continuous monitoring. One interesting application movement can be recognised and separated with the use of Principle
of wearable sensors in sports and exercise is to use the data collected Component Analysis (PCA) and Micro-Doppler (m-D) eect but, its
from sensors for mapping real-world activities to the games, then, eectiveness is still to be veried for real-time application (Shi et al.,
developing the activity monitoring system in such a way that it can 2016; Mukhopadhyay, 2015). Human activity recognition has been in
produce an enjoyable game. Some authors have proposed the devel- some way, individualized. It means, the most of the systems can be
opment of a truly virtual mobile sports environment game tablet- used only for a single user at a time. Although social networks give
based exergame with wearable human body sensors (Mortazavi et al., information eective to recognize collective activities (Lane et al.,
2014). There was a time when sweat rate measurement for athletes was 2011) which can be considered one step further. A exible force sensor
possible only in laboratories. Now, it is possible to measure sweat rate was developed to assess the feasibility of detection of improper sitting
using wearable devices outside the laboratories also (Ermes et al., posture. The sensor was based on piezo-resistive capacitive lm (Lee
2008; Salvo et al., 2010; Strohrmann et al., 2012). It has been found and Shin, 2016). The study can be further extended in order to increase
that exergames can be helpful to strengthen the children with autism the resolution with the increase in number of sensors and the area of
spectrum disorders physically and mentally. A novel wearable sensor measurement. The sensor platform can be optimized by determining
based Automatic Ingestion Monitoring (AIM) system has been reported the size and position of the sensor. A wearable EEG was introduced
for unbiased monitoring of ingestive activity/behavior in normal life based on the In-Ear-EEG recording concept.
(Fontana et al., 2014). It integrates three sensor modalities namely a It was a generic device and can be used to record all the responses
sensor for jaw motion, a sensor for hand gesture recognition, and an that may be acquired from standard EEG (Goverdovsky et al., 2016).
accelerometer. These sensors interface to a smartphone through Fig. 9 shows the evaluation of EEG system from conventional to In-
wireless network. The development was aimed to correct known Ear-EEG.
ingestive behaviors causing weight gain with the help of a novel Recently, a multi-tasking wearable device is developed which
behavioral modication tool. It will also help the patients with eating monitors the health of person's heart as well as assess the position of
disorders by studying their free-living food consumption. The possibi- the person (Mao et al., 2008). To monitor dental cavities and other
lity of wearable computers has been discussed which could share dental plaque, a health monitoring apparatus is designed. It is an oral
thoughts and sensations (Bleicher, 2014). It would be like wearing a monitoring system (Nanjundappa et al., 2016). A data fusion algorithm
computer on our arm. This will be personal and intimate and will be based fall detection wearable system is developed for elderly persons.
based on technologies that attempt to colonize our whole body. It may The developed device uses MEMS, Kalman lter, Code Division
track our body movements, listen to our heartbeat and put our body on Multiple Access (CDMA) network to achieve ecient detection
line. A patent MD-based Brain Sentry represents a crucial concept of (Wang and Qin, 2016). In very recent years, people are working on
wearable sensors which uses accelerometers to measure acceleration resolving all these above mentioned major challenges for wearable
during physical activity. The Brain Sentry helmet-mounted sensors give computing such as power line interference removal, selection of best
an alert alarm when an athlete suers an unusual rapid and potentially wearing location (Chimeno and Palls-areny, 2000). For continuous
dangerous acceleration of the head. The alarm indicates possible injury monitoring of physiological signals with wearable devices,
in the head of the player. The sensor is compact enough and weighs Power Line interference (PLI) removal is of important considera-
only one ounce. It is waterproof and the batteries are long-lasting. It tion. Keeping this in mind, a work has been presented for evaluation of
can work for a whole year without charging, meaning no maintenance dierent techniques of PLI ltering to acquire better quality in
by the person (Boyle, 2014). Mindful wearables have been designed heterogeneous physiological signals (Tomasini et al., 2016).
for improving physical health as well as mental well-being. Meditation A number of neurological disorders can be diagnosed with bio-
apps together with conventional EEG are being designed with the aim potential signals EEG, EOG, and EMG. For ECG recording, we have
to help in concentration build-up and self-regulation skills (Fernandez, many wireless systems as shown in Table 1. However, for bio-potential
2015). To recognize the facial expression of human being, Step-wise signals such as EEG, EOG, and EMG recording, most of the platforms
Linear Discriminant Analysis (LDA) and Hidden Conditional Random provide wired system. Only few manufacturers such as Compumedics
Fields (HCRF) had been used and validated oine. However, in real- provide Bluetooth system and Siesta's Ethernet radio link. A list is
world environment, its performance is not investigated till now. To shown in Table 2.
solve these problems, a robust, real-time subdivision technique may be Sometimes, wearing these add-on devices in public places may be
needed. Furthermore, in an actual environment, the facial frames may uneasy or uncomfortable to the user (Knight and Baber, 2005). In a
303
P. Kumari et al. Biosensors and Bioelectronics 90 (2017) 298307
Table 1
Commercial ECG recording platforms (Varadan et al., 2016).
Phillips Page writer TC50 ECG 12 channels of ECG USB memory stick (upto 16 GB) No
GE Healthcare MARS Ambulatory ECG System (SEER 12, SEER light) 312 channels of ECG 1 GB internal and optical DVD storage No
Imec Secure Digital Input Output 1channel ECG 16 GB Yes
AliveCor AliveCor 1 channel ECG 16 GB Yes
Phillips EASI (Philips DigiTrak XT) 4 channels ECG 256512 MB No
study, some common wearing locations were investigated. According to hormones release in blood stream and alters blood pressure and heart
statistical results, a noticeable alteration in elderly people's attitudes is rate. This eye gaze-induced stress level can be evaluated by monitoring
observed towards these add-on devices attached to dierent locations bio potential signals ECG and EOG (Aggarwal et al., 2014). To help the
on their body. The wrist was the most acceptable location for wearable elderly or disabled persons, a real-time EOG based alarm system has
device by the users (Fang and Chang, 2016). been designed. Further, the work can be extended to various other
Many medical research also points to the importance of doctor- control applications for needy people (Bobade and Khirwadkar, 2016).
patient interaction (Chaudhry et al., 2006; Cloudy Forecast: EOG technique is used to measure the resting potential of retina (Mala
Predictions for Big Data in Large and Small Medical Practices, and Latha, 2014). Wide applications of EOG also include activity
2013; Niksch et al., 2014). Whether the use of wearables by patients recognition (Bulling et al., 2011), virtual key board (Usakli and Gurkan,
might aect the doctor-patient interaction or whether this would 2010), controlling of expert multitask gadget (Gandhi et al., 2010) and
inuence patient behaviors too and therefore health results are many more.
important questions (Loos and Davidson, 2016). Now a days, monitoring of human activity through fusion of a
Neurological disorders like sleep disorder, drowsiness can also be number of bio potential signals are very much popular. A multimodal
monitored by wearable wireless systems. According to National fusion of EOG and EEG information has been shown as a robust
Institute of Health (NIH), millions of Americans suer from sleep approach for recognition of reading activity in day-to-day life (Bulling
disorders (Shen et al., 2006). For diagnosing sleep disorders, dierent et al., 2012). For driving fatigue detection, a fusion of EEG signal and
approaches are used such as polysomnography (PSG) and home sleep forehead EOG signal (Huo et al., 2016) has been used which shows
test (HST). PSG is considered as a standard approach for monitoring better performance than solely using EEG (Wang et al., 2016) and
sleep disorders or sleep patterns. But this approach has many forehead EOG signal (Zhang et al., 2015). A wearable wireless brain-
disadvantages like: cost involved is very high, the patient has to stay computer interface system was developed for hybrid control of a robot
in the laboratory for the whole night which may cause discomfort or based on EEG and EOG signals (Oh et al., 2012). In this system, speed
inconvenience to the patient and that may also aect the test. Also the and stopping of the robot were controlled by brain signals (EEG) and
waiting time for the test is very long due to unavailability of sucient right and left movements were controlled by EOG signals. A human-
capacity of sleep laboratories (Flemons et al., 2004). The HST is machine interface system was developed which was based on wearable
performed at home. So, it has overcome the problem of inconvenience sensor and only one channel EOG. The usability of the system is much
of patient, long waiting time and cost involved. But it has lack of real higher as it can enhance the comfort and wearability of the system
time (RT) monitoring of sleep patterns and less physiological informa- (Guo et al., 2016). In this work, individually optimized threshold for
tion. The real time monitoring of signals from remote locations can be each subject improved the classication performance, but the obtained
achieved by the concept of combining two wireless communication classication accuracy (84%) and Information Transfer Rate (ITR)
standards, on is for building WPAN (Wireless Personal Area Network)/ (13 bits/min) was not sucient to use this system for real-world
WBAN (Wireless Body Area Network) and other is for WAN (Wide applications. Electrooculogram (EOG), electromyogram (EMG), and
Area Network). Wireless wearable biosensors can also be used to glossokinetic potential (GKP) based multimodal interface was used for
monitor drowsiness which is very useful in improving safety. People, human-computer interface to improve the information capacity. These
like security guards, night shift workers, drivers who need to stay kinds of multimodal interface approach may improve the information
awake during night need drowsiness monitoring systems. According to capacity as well as its robustness and usability. The author (Nam et al.,
National Highway Trac safety Administration (NHTSA), approxi- 2014) himself has suggested that the performance and the capacity of
mately 25% of road accidents involve some form of drowsiness, the developed system can further be enhanced if it is integrated with
inattention, sleep or fatigue (Ranney et al., n.d.; The Role of Driver other modalities such as EEG. A robot control system was developed
Fatigue in Commercial Road Transport Crashes, 2001). Psychomotor using two modalities Electrooculography and Electromyogram. EOG is
Vigilance Test (PVT) is one of the tests used to assess the quality of using for moving the robot joint angles and EMG is using for object
sleep (Kamen, 2004). In a study, it has been found that continuous eye grasping. However, it was found that the EOG and EMG signals are
gaze triggers the Autonomic nervous system (ANS) which causes hard to discriminate for the robot control system (Sasaki et al., 2015).
Table 2
Commercial EEG, EOG and EMG recording platforms (Varadan et al., 2016).
304
P. Kumari et al. Biosensors and Bioelectronics 90 (2017) 298307
The combination of EOG interface with RFID technology in shared physiological signal cannot have all the information required for a
control architecture was used in an assistive robot. With this approach, particular task.
interaction with objects can be possible without using any kind of
motor related movement and the number of commands were increased 7. Scope of future work
that can be generated by the EOG interface alone (Iez et al., 2012).
There are a lot of works centered in solving accessibility issues
6. Conclusions using rehabilitation robotics or developing alternative communication
methods with the environment. Humanmachine interfaces are used
It can be concluded from the above discussion that human activity to interact with external devices aimed at helping handicapped people
recognition is an emerging area of research which is moving towards or elderly persons. Ocular movements can be used to generate
the development of an intelligent and smart Healthcare Platform commands to control external devices as in progressive neurodegen-
Integrated in small devices for providing comfort to the patients as erative diseases, the brain and spinal cord nerve cells are aected but
well as elderly persons, for their well-being and independent living. A the eye movements remain intact. Since most completely paralyzed
signicant commercial development and progress have been already people can still move their eyes, EOG is a signal that can be practically
reported. Still, we have many challenges and unsolved issues. Presently used for controlling the prosthetic devices. The advantage of EOG in
available wearable sensors have solved the purpose to some extent. terms of accuracy and complexity is quite important so it is one of the
However, they are also not very much cost eective and ecient from most commonly used methods to detect eye movement. The combina-
all the aspects which have been discussed in this paper. These unsolved tion of an EOG interface with Radio-frequency identication (RFID)
issues motivate the development of new wearables having some new technology in shared control architecture is used in recent research
techniques which can be applicable in health-care systems or HAR works. However, a single EMG, EEG or EOG-based system can only
systems and solve the purpose eciently for more realistic environ- manage one certain kind of task. It is rather dicult to have a
ments. It is expected from previous studies that many more user- universally robust system applicable to dierent situations.
acceptable, high-performance, low cost wearable devices will be avail- Therefore, multimodal system will be a more eective approach.
able for recognition of variety of activities. Surveys also predict that the Shared control with multimodal interface can be a better approach
interest, and consequently, the use of wearable devices will be for generating complex control commands to optimally guide an
increased in near future. At the same time, the cost of wearable devices external device or application. Wearable systems can be designed to
is expected to fall due to its wide applications in real-time. As much as control the dierent kind of objects based on multimodal interface and
technology will mature, novelty in medical science will be increased, shared control architecture where multimodal interface can take
further increase in integration of medical sensors and electronics decisions about the movement of a robot for a particular application
instruments will be witnessed and consequently, wearables will be and the interaction with objects can be assisted by RFID technology.
further smaller. It will support home based physiological data collec- More modalities can be added in future to further enhance the
tion, preventive healthcare programs and also facilitate remote care. controlling commands and make the product more feasible and usable.
The future of medical sciences is likely to be packed in the huge
prospective of the world's smallest sensors and wearable devices References
where technology shorten to lengthen, and a generation lifted on
gadgets waste away. To provide a better alternative to the healthcare Aggarwal, Y., Singh, N., Ghosh, S., Sinha, R.K., 2014. Eye gaze-induced mental stress
system, development of comfortable, low cost wearable devices are alters the heart rate variability analysis. J. Clin. Eng. 39, 7989. http://dx.doi.org/
10.1097/JCE.0000000000000023.
needed that can measure and continuously record the electrical activity Alert Devices for the Elderly [WWW Document], 2016. Med. Alert Syst. Rev. Site. URL
of human body as well as can transmit the obtained data wirelessly to a http://medicalalertsystemshq.com/blog/medical?alert?devices?for?the?elderly.
computer, where it will be displayed in real time. If activity samples of a html.
Bagade, P., Banerjee, A., Gupta, S.K.S., 2014. Optimal design for symbiotic wearable
signicant number of users from a predened area like a city, or a state wireless sensors. In: Proceedings of the 2014 11th International Conference on
could be gathered as samples, the information obtained from Wearable and Implantable Body Sensor Networks, IEEE Computer Society. pp. 132
these samples could be used to estimate health conditions, early 137.
Bleicher, A., 2014. Beyond words: Wearable computers will let us share thoughts and
diagnosis of some disorders, exercise habits. Hence further, this type sensations. IEEE Spectr., 6671.
of participatory human-centered application would be free from Bobade, J.R., Khirwadkar, M.D., 2016. Design and implementation of electrooculogram
economic-incentive-based method. The users will participate willingly based alarm system for disabled. Int. J. Adv. Res. Comput. Eng. Technol. 5,
872874.
in the system since they would be receiving the suggestions, informa-
Bonato, P., 2010. Wearable sensors and systems. IEEE Eng. Med. Biol. Mag., 2536.
tion related to their health conditions and exercises to improve their http://dx.doi.org/10.1109/MEMB.2010.936554.
physiological performance. Such gathered data from a sucient Boyle, J.A., 2014. Brain Sentry Licenses Breakthrough Wearable Sensor Technology from
number of users can be used to train machine learning classication Johns Hopkins University.
Bulling, A., Ward, J., Gellersen, H., Troster, G., 2011. Eye movement analysis for activity
algorithms or soft computing techniques to enhance the overall recognition using electrooculography. IEEE Trans. Pattern Anal. Mach. Intell. 33,
accuracy and consequently, to improve health diagnosis. EOG signal 741753.
has wide applications in clinic as well as in engineering such as Bulling, A., Ward, J.A., Gellersen, H., 2012. Multimodal recognition of reading activity in
transit using body-worn sensors. ACM Trans. Appl. Percept. 9, 2:12:21. http://
diagnosis of eye injuries, eye diseases, eye-controlled engineering dx.doi.org/10.1145/2134203.2134205.
devices viz. cursor mouse. In spite of that, the use of an EOG interface Chaudhry, B., Wang, J., Wu, S., Maglione, M., Mojica, W., Roth, E., Morton, S.C.,
is still not enough capable of performing tasks involving complex Shekelle, paul G., 2006. Systematic review: impact of health information technology
on quality, eciency, and costs of medical care. Ann. Intern. Med. 144, 742752.
control commands to guide an external device optimally. One solution Chen, B., Patel, S., Buckley, T., Rednic, R., Mcclure, D.J., Shih, L., Tarsy, D., Welsh, M.,
for these limitations is shared control approach. E.g. combining EOG Bonato, P., 2011. A web-based system for home monitoring of patients with
and Radio-frequency identication (RFID) technology. Shared control Parkinson s disease using wearable sensors. IEEE Trans. Biomed. Eng. 58, 831836.
Chimeno, M.F., Palls-areny, R., 2000. A comprehensive model for power line
has a wide range of applications. In robotics, it is used with multi-agent interference in biopotential measurements. IEEE Trans. Instrum. Meas. 49,
systems on cooperative tasks. Shared control is also useful for disabled 535540.
people, e.g., to aid blind people and to improve mobility. In future Choujaa, D., Dulay, N., 2008. TRAcME: temporal activity recognition using mobile phone
data. In: Proceedings of the IEEE/IFIP International Conference on Embedded
research, one can have the opportunity to work for minimization of
Ubiquitous Computing. pp. 119126. http://dx.doi.org/10.1109/EUC.2008.33.
positions of EOG electrodes and design of real time wearable devices Cloudy Forecast : Predictions for Big Data in Large and Small Medical Practices [WWW
based on EOG signal. To increase the performance of recognition, more Document], 2013. Cern. Ambul.
multimodal fusion of physiological signals is sought, since a single Cook, B.S., Le, T., Palacios, S., Traille, A., Tentzeris, M.M., 2013. Only skin deep. IEEE
305
P. Kumari et al. Biosensors and Bioelectronics 90 (2017) 298307
Macrow. Mag., 103114. Mariani, B., Jimenez, M.C., Vingerhoets, F.J.G., Aminian, K., 2013. On-shoe wearable
Cunningham, P., Delany, S.J., 2007. k-Nearest Neighbour Classiers. Dublin. sensors for gait and turning assessment of patients With Parkinsons disease. IEEE
Englebienne, T.L.M.V.K.G., Krose, B.J.A., 2010. An activity monitoring system for elderly Trans. Biomed. Eng. 60, 155158.
care using generative and discriminative models. J. Pers. Ubiquitous Comput. 14, Marquardt, D., 1963. an algorithm for least-squares estimation of nonlinear
489498. http://dx.doi.org/10.1007/s00779-009-0277-9. paramenters. J. Soc. Ind. Appl. Math. 11, 431441.
Ermes, M., Parkka, J., Mantyjarvi, J., Korhonen, I., 2008. Detection of daily activities and Mobile phones to come with panic button from 2017, 2016. Econ. Times Bur. pp. 25.
sports with wearable sensors in controlled and uncontrolled conditions. IEEE Trans. Mortazavi, B., Nyamathi, S., Lee, S.I., Wilkerson, T., Ghasemzadeh, H., Sarrafzadeh, M.,
Inf. Technol. Biomed. 12, 2026. 2014. Near-realistic mobile exergames with wireless wearable sensors. IEEE J.
Fang, Y.-M., Chang, C.-C., 2016. Users' psychological perception and perceived Biomed. Heal. Inform. 18, 449456.
readability of wearable devices for elderly people. Behav. Inf. Technol., 18. http:// Mukhopadhyay, S.C., 2015. Wearable sensors for human activity monitoring: a review.
dx.doi.org/10.1080/0144929X.2015.1114145. IEEE Sens. J. 15, 13211330.
Fernandez, A., 2015. Mindful wearables [WWW Document]. Sharp Brains. URL Nam, Y., Koo, B., Cichocki, A., Choi, S., 2014. GOM-face: GKP, EOG, and EMG-based
http://sharpbrains.com/blog/2015/11/10/10-neurotechnologies-about-to- multimodal interface with application to humanoid robot control. IEEE Trans.
transform-brain-enhancement-and-brain-health/. Biomed. Eng. 61, 453462. http://dx.doi.org/10.1109/TBME.2013.2280900.
Flemons, W.W., Douglas, N.J., Kuna, S.T., Rodenstein, D.O., Wheatley, J., 2004. Access Nanjundappa, R., Franklin, R., Dharmapurikar, V.A., Singh, S., 2016. Oral health
to diagnosis and treatment of patients with suspected sleep apnea. Am. J. Respir. Monitoring Method and apparatus and Electronic Device Using the Same.
Crit. Care Med. 169, 668672. http://dx.doi.org/10.1164/rccm.200308-1124PP. Nemati, E., Deen, M.J., Mondal, T., 2012. A wireless wearable ECG sensor for long-term
Fontana, J.M., Farooq, M., Sazonov, E., 2014. Automatic ingestion monitor: a novel applications. IEEE Commun. Mag., 3643.
wearable device for monitoring of ingestive behavior. IEEE Trans. Biomed. Eng. 61, Niksch, A.L., Rothman, B.S., Davidson, S.J., 2014. The value of remote patient
17721779. monitoring (RPM) physicians' perspectives. Healthc. Inf. Manag. Syst. Soc., 15.
Gandhi, T., Trikha, M., Santhosh, J., Anand, S., 2010. Development of an expert Oh, S., Kumar, P.S., Kwon, H., Varadan, V.K., 2012. Wireless brain-machine interface
multitask gadget controlled by voluntary eye movements. Expert Syst. Appl. 37, using EEG and EOG: Brain wave classication and robot control. In: SPIE
42044211. http://dx.doi.org/10.1016/j.eswa.2009.11.082. Proceedings on Nanosensors, Biosensors, and Info-Tech Sensors and Systems. pp.
Goverdovsky, V., Looney, D., Kidmose, P., Mandic, D.P., 2016. In-ear EEG from 18. http://dx.doi.org/10.1117/12.918159
viscoelastic generic earpieces: robust and unobtrusive 24/7 monitoring. IEEE Sens. Patel, S., Lorincz, K., Hughes, R., Huggins, N., Growdon, J., Standaert, D., Akay, M., Dy,
J. 16, 271277. J., Welsh, M., Bonato, P., Member, S., 2009. Monitoring motor uctuations in
Gunn, S.R., 1998. Support Vector Machines for Classication and Regression. patients with Parkinson s disease using wearable sensors. IEEE Trans. Inf. Technol.
Guo, X., Pei, W., Wang, Y., Chen, Y., Zhang, H., Wu, X., Yang, X., Chen, H., Liu, Y., Liu, Biomed. 13, 864873.
R., 2016. A human-machine interface based on single channel EOG and patchable Patel, S., Park, H., Bonato, P., Chan, L., Rodgers, M., 2012. A review of wearable sensors
sensor. Biomed. Signal Process. Control 30, 98105. http://dx.doi.org/10.1016/ and systems with application in rehabilitation. J. Neuroeng. Rehabil. 9, 21. http://
j.bspc.2016.06.018. dx.doi.org/10.1186/1743-0003-9-21.
Hayward, J., Chansin, D.G., 2016. Wearable Sensors 2016-2026: Market Forecasts, Peixoto, P., Batista, J., Araujo, H.J., 2001. Real-time human activity monitoring
Technologies, Players [WWW Document]. URL http://www.idtechex.com/ exploring multiple vision sensors. Rob. Auton. Syst. 35, 221228. http://dx.doi.org/
research/reports/wearable-sensors-2016-2026-market-forecasts-technologies- 10.1016/S0921-8890(01)00117-8.
players-000470.asp. Quazi, M.T., 2012. Human Emotion Recognition Using Smart Sensors. Massey
Hayward, J., Das, R., Holland, G., 2015. Wearable Technology 20152025 : Technologies university, New Zealand.
, Markets, Forecasts [WWW Document]. URL http://www.idtechex.com/research/ Ramasamy, V., Gowda, C., Noopuran, S., 2014. The basics of designing wearable
reports/wearable?technology?2015?2025?technologies?markets?forecasts?000427. electronics with microcontrollers [WWW Document]. Cypress Semicond. URL
asp. http://www.embedded.com/print/4431259
Hopeld, J.J., 1988. Articial neural networks. IEEE Circuits Devices Mag., 310. Ranney, T.A., Garrott, W.R., Goodman, M.J., n.d. NHTSA Driver Distraction Research:
Huo, X., Zheng, W., Lu, B., 2016. Driving fatigue detection with fusion of EEG and Past, Present and Future. 2001 pp. 18, http://www-nrd.nhtsa.dot.gov/pdf/esv/
forehead EOG. In: Proceeding of International Joint Conference on Neural Networks esv17/proceed/00177.pdf
(IJCNN-16). Rodgers, M.M., Pai, V.M., Conroy, R.S., 2015. Recent advances in wearable sensors for
Iez, E., beda, A., Azorn, J.M., Perez-vidal, C., 2012. Assistive robot application based health monitoring. IEEE Sens. J. 15, 31193126.
on an RFID control architecture and a wireless EOG interface. Rob. Auton. Syst. 60, Salvo, P., Francesco, F., Di, Costanzo, D., Ferrari, C., Trivella, M.G., Rossi, D. De, 2010. A
10691077. http://dx.doi.org/10.1016/j.robot.2012.05.006. wearable sensor for measuring sweat rate. IEEE Sens. J. 10, 15571558.
Iglesias, J., Cano, J., Bernardos, A.M., Casar, J.R., 2011. A ubiquitous activity-monitor to Sarkar, J., Vinh, L.T., Lee, V.Y., 2011. GPARS: a general-purpose activity recognition
prevent sedentariness. IEEE Conf. Pervasive Comput. Commun., 319321. system. Appl. Intell. 35, 242259. http://dx.doi.org/10.1007/s10489-010-0217-4.
Jatob, L.C., Gromann, U., Kunze, C., Ottenbacher, J., Stork, W., System, A.M., 2008. Sasaki, M., SAuhaimi, M.S.B.A., Matsushita, K., Ito, S., Rusydi, M.I., 2015. Robot control
Context-aware mobile health monitoring: evaluation of dierent pattern recognition system based on electrooculography and electromyogram. J. Comput. Commun. 3,
methods for classication of physical activity. Annu. Int. IEEE EMBS Conf., 113120.
52505253. Seoane, F., Mohino-herranz, I., Ferreira, J., Alvarez, L., Llerena, C., Gil-pita, R., 2014.
Juha, P., Ermes, M., Korpipaa, P., Mantyjarvi, J., Peltola, J., 2006. Activity classication Wearable biomedical measurement systems for assessment of mental stress of
using realistic data From Wearable sensors. IEEE Trans. Inf. Technol. Biomed. 10, combatants in real time. Sensors 40, 71207141. http://dx.doi.org/10.3390/
119128. s140407120.
Kamen, G., 2004. Electromyographic kinesiology. In: Robertson, L.D., Tocco, A.N. (Eds.), Shen, J., Barbera, J., Shapiro, C.M., 2006. Distinguishing sleepiness and fatigue: focus on
Research Methods in Biomechanics. Human Kinetics Publication, Champaign, IL, denition and measurement. Sleep Med. Rev. 10, 6376. http://dx.doi.org/10.1016/
171181. j.smrv.2005.05.004.
Knight, J.F., Baber, C., 2005. A tool to assess the comfort of wearable computers. Hum. Shi, X., Zhou, F., Tao, M., Zhang, Z., 2016. Human movements separation based on
Factors Ergon. Soc. 47, 7791. http://dx.doi.org/10.1518/0018720053653875. principle component analysis. IEEE Sens. J. 16, 20172027.
Lane, N.D., Xu, Y., Campbell, A.T., Choudhury, T., Eisenman, S.B., 2011. Exploiting Siddiqi, M.H., Ali, R., Khan, A.M., Park, Y., Lee, S., 2015. Human facial expression
social networks for large-scale human behavior modeling. IEEE Pervasive Comput. recognition using stepwise linear discriminant analysis and hidden conditional
10, 4553. random elds. IEEE Trans. Image Process. 24, 13861398.
Lara, D., Labrador, M.A., 2013. A survey on human activity recognition using wearable Strohrmann, C., Harms, H., Kappeler-setz, C., Tr, G., 2012. Monitoring kinematic
sensors. IEEE Commun. Surv. Tutor. 15, 11921209. changes with fatigue in running using body-worn sensors. IEEE Trans. Inf. Technol.
Lee, B.W., Shin, H., 2016. Feasibility study of sitting posture monitoring based on Biomed. 16, 983990.
piezoresistive conductive lm-based exible force sensor. IEEE Sens. J. 16, 1516. The Role of Driver Fatigue in Commercial Road Transport Crashes, 2001.
Lin, C., Yang, Y.C., Wang, J., Yang, Y., 2012. A wearable sensor module with a neural- Toh, W.Y., Tan, Y.K., Koh, W.S., Siek, L., 2014. Autonomous wearable sensor nodes with
network- based activity classication algorithm for daily energy expenditure exible energy harvesting. IEEE Sens. J. 14, 22992306.
estimation. IEEE Trans. Inf. Technol. Biomed. 16, 991998. Tolstikov, A., Hong, X., Biswas, J., Nugent, C., Chen, L., Parente, G., 2011. Comparison of
Lin, Y., 2009. Decision Making in assistive environments using multimodal observations. fusion methods based on DST and DBN in human activity recognition. J. Control
In: Proceedings of the Petra '09 ACM. pp. 18. Theory Appl. 9, 1827. http://dx.doi.org/10.1007/s11768-011-0260-7.
Liu, G., Huang, B., Wang, L., 2011. A wearable respiratory biofeedback system based on Tomasini, M., Benatti, S., Milosevic, B., Farella, E., Benini, L., 2016. power line
generalized body sensor network. Telemed. J. E. Health, 348357. http:// interference removal for high-quality continuous biosignal monitoring with low-
dx.doi.org/10.1089/tmj.2010.0182. power wearable devices. IEEE Sens. J. 16, 38873895.
Loos, J.R., Davidson, E.J., 2016. Wearable health monitors and physician-patient Ugulino, W., Cardador, D., Vega, K., Velloso, E., Milidiu, R., Fuks, H., 2012. Wearable
communication: the physicians perspective. In: Proceeding of the 2016 49th Hawaii computing: accelerometers' data classication of body postures and movements.
International Conference on System Sciences (HICSS)HICSS '16. pp. 33893399. Adv. Artif. Intell. 7589, 5261. http://dx.doi.org/10.1007/978-3-642-34459-6.
http://dx.doi.org/10.1109/EUC.2008.3310.1109/HICSS.2016.422. Usakli, A.B., Gurkan, S., 2010. Design of a novel ecient human computer interface:
Mala, S., Latha, K., 2014. Feature selection in classication of eye movements using an electrooculagram based virtual keyboard. IEEE Trans. Instrum. Meas. 59,
electrooculography for activity recognition. Comput. Math. Methods Med. 2014, 19 20992108.
. http://dx.doi.org/10.1155/2014/713818. Uslu, G., Dursunoglu, H.I., Altun, O., Baydere, S., 2013. Human activity monitoring with
Malhi, K., 2010. Wireless Sensors Network Based Physiological Parameters Monitoring wearable sensors and hybrid classiers. Int. J. Comput. Inf. Syst. Ind. 5, 345353.
System. Massey University, New Zealand. Varadan, V.K., Rai, P., Oh, S.C., Kumar, P.S., 2016. Wearable technology and mobile
Mao, M., Chuo, Y., Kaminska, B., 2008. Multi-functional wearable device for heart health platform for human health monitoring. Forum Electromagn. Res. Methods Appl.
and position assessment. NSTI Nanotech. 2, 615618. Technol. 16, 138.
306
P. Kumari et al. Biosensors and Bioelectronics 90 (2017) 298307
Velloso, E., Bulling, A., Gellersen, H., Ugulino, W., 2013. Qualitative activity recognition Wang, X., Qin, H., 2016. Implementation of fall detection system based on data fusion
of weight lifting exercises. In: Proceeding of the International Conference in technology. Int. J. u- e- Serv. Sci. Technol. 9, 18. http://dx.doi.org/10.14257/
Cooperation with SIGCHI (Augmented Human13). ijunesst.2016.9.4.01.
Versel, N., 2012. Panic buttons for seniors must go [WWW Document]. Yang, J., Lee, J., Choi, J., 2011. Activity recognition based on RFID object usage for
MobiHealthNews. URL http://mobihealthnews.com/19397/panic?Buttons?For? smart mobile devices. J. Comput. Sci. Technol. 26, 239246. http://dx.doi.org/
Seniors?Must?Go. 10.1007/s11390-011-1126-7.
Wang, L., Zheng, W., Ma, H., Lu, B., 2016. Measuring sleep quality from EEG with Zhang, Y., Gao, X., Zhu, J., Zheng, W., Lu, B., 2015. A Novel Approach to Driving Fatigue
machine learning approaches. In: Proceedings of the International Joint Conference Detection Using Forehead EOG. In: Proceedings of the International IEEE/EMBS
on Neural Networks (IJCNN-16). Conference on Neural Engineering. pp. 707710.
307